{"id":"W2888190576","doi":"10.2196/11021","title":"Extraction and Standardization of Patient Complaints from Electronic Medication Histories for Pharmacovigilance: Natural Language Processing Analysis in Japanese","year":2018,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Pharmacovigilance and Adverse Drug Reactions","field":"Pharmacology, Toxicology and Pharmaceutics","cited_by":41,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Pharmacovigilance; Standardization; Natural language processing; Computer science; Information extraction; Medicine; Adverse effect; Pharmacology","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005285126,0.0001452427,0.0003025258,0.0002478183,0.0001504219,0.00001300467,0.0001305046,0.0001963022,0.0003060259],"category_scores_gemma":[0.0001385075,0.0001324758,0.00006381197,0.0004875769,0.0002839581,0.0004178612,0.00003274882,0.0004933617,0.000004834807],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002053925,"about_ca_system_score_gemma":0.0001826697,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003587418,"about_ca_topic_score_gemma":0.0001047699,"domain_scores_codex":[0.9984725,0.00008602015,0.0006260917,0.0001338638,0.0003642048,0.0003173306],"domain_scores_gemma":[0.9989316,0.0002661311,0.0003845801,0.00009806707,0.0001557439,0.0001638532],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004124891,0.00167541,0.02736715,0.001500481,0.002297898,0.00002275796,0.3942197,0.001906691,0.04400938,0.0005610005,0.006176738,0.5161379],"study_design_scores_gemma":[0.005590407,0.0002461513,0.002905033,0.0001354834,0.0009992479,0.00001899285,0.02123774,0.780346,0.03798164,0.0001759685,0.1498695,0.0004938247],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9936566,0.000686144,0.003866444,0.0002310463,0.0004576298,0.0004559613,0.0001255627,0.00005115456,0.0004694362],"genre_scores_gemma":[0.997906,0.0002293311,0.0003650496,0.0008042471,0.0001931143,0.00009242025,0.0003712167,0.000008830135,0.00002982604],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7784393,"threshold_uncertainty_score":0.5402208,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02668859490989499,"score_gpt":0.4392594911369813,"score_spread":0.4125708962270863,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}